Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events or significant moments in time

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.82
    reau
    -0.82
    vana
    -0.82
    eele
    -0.81
    athy
    -0.80
    assium
    -0.78
    eeper
    -0.77
     teasp
    -0.77
    emouth
    -0.76
    EEP
    -0.75
    POSITIVE LOGITS
     mankind
    1.21
     humankind
    1.07
     warfare
    0.97
     colonialism
    0.87
     religions
    0.83
     civilizations
    0.82
     Warfare
    0.80
     Mankind
    0.77
     science
    0.76
     americ
    0.76
    Act Density 0.068%

    No Known Activations